© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130344
    Prev
    Next
    INDEX
    Explanations

    monitoring applications

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on occurrences of the word “monitoring.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    end
    -3.13
    可以
    -3.03
    ため
    -2.78
    ዡ
    -2.73
    埽
    -2.58
    人的
    -2.56
    的
    -2.56
    пом
    -2.55
     There
    -2.53
     стал
    -2.52
    POSITIVE LOGITS
    摭
    3.73
    趼
    3.63
    聍
    3.45
    ญี่ป
    3.28
    ༀ
    3.19
    獃
    3.14
    摃
    3.05
    屜
    2.95
    汭
    2.94
    欵
    2.89
    Activations Density 0.009%

    No Known Activations